Papers with Code 아카이브

Adversarial Text

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/AI-secure/T3

공식 코드

T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack

https://github.com/CatherineWong/dancin_seq2seq

공식 코드

DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation

https://github.com/QData/TextAttack

공식 코드

BAE: BERT-based Adversarial Examples for Text Classification

https://github.com/QData/TextAttack-Search-Benchmark

공식 코드

Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples

https://github.com/QData/TextAttack/blob/master/textattack/attack_recipes/bae_garg_2019.py

공식 코드

BAE: BERT-based Adversarial Examples for Text Classification

https://github.com/QData/deepWordBug

공식 코드

Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers

https://github.com/RishabhMaheshwary/hard-label-attack

공식 코드

Generating Natural Language Attacks in a Hard Label Black Box Setting

https://github.com/RussianNLP/TAPE

공식 코드

TAPE: Assessing Few-shot Russian Language Understanding

https://github.com/Spinozaaa/AdvI2I

공식 코드

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models

https://github.com/Tangyiming205069/controllable-seo

공식 코드

StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization

https://github.com/Top-Ranger/text_adversarial_attack

공식 코드

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

https://github.com/advattack/bu-spo

공식 코드

Semantic-Preserving Adversarial Text Attacks

https://github.com/agencyenterprise/promptinject

공식 코드

Ignore Previous Prompt: Attack Techniques For Language Models

https://github.com/ai-secure/semattack

공식 코드

SemAttack: Natural Textual Attacks via Different Semantic Spaces

https://github.com/aisecure/AdvCodec

공식 코드

T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack

https://github.com/akil003/bert-attack

공식 코드

Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted Misclassification

https://github.com/aminbigdeli/empra

공식 코드

EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models

https://github.com/apple/axlearn/blob/main/axlearn/vision/imagenet_adversarial_text/

공식 코드

Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness

https://github.com/captaincuong/robusttext_acl2024

공식 코드

A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models

https://github.com/cecilialeiqi/adversarial_text

공식 코드

Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification

https://github.com/chenwu98/agent-attack

공식 코드

Dissecting Adversarial Robustness of Multimodal LM Agents

https://github.com/collinzrj/adversarial_decoding

공식 코드

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives

https://github.com/ecrows/cgtext-detection-adv

공식 코드

Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers

https://github.com/ellezwq/mmcoa

공식 코드

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

https://github.com/gmum/mango

공식 코드

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks

https://github.com/google-research/retvec

공식 코드

RETVec: Resilient and Efficient Text Vectorizer

https://github.com/google/unisim

공식 코드

RETSim: Resilient and Efficient Text Similarity

https://github.com/javirandor/wdr

공식 코드

"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks

https://github.com/jind11/TextFooler

공식 코드

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

https://github.com/jonrusert/binaryselect

공식 코드

BinarySelect to Improve Accessibility of Black-Box Attack Research

https://github.com/levelower/vfa

공식 코드

Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation

https://github.com/lionel-w2/fap

공식 코드

Few-Shot Adversarial Prompt Learning on Vision-Language Models

https://github.com/metaphors/TSAttack

공식 코드

TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity

https://github.com/mingzelucasni/fba

공식 코드

Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process

https://github.com/norahalshahrani/bert_synonym_attack

공식 코드

Arabic Synonym BERT-based Adversarial Examples for Text Classification

https://github.com/optml-group/qf-attack

공식 코드

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.